The talk archive.

Why your product needs an AI product manager, and why it should be you

James Lowe

Enterprise · Safety and governance · Industry applications

Will Agent Evaluation via MCP Stabilize Agent Networks?

Ari Heljakka

Evals · Safety and governance · APIs, MCP, and protocols

Windsurf everywhere, doing everything, all at once

Kevin Hou

Developer workflows and testing · APIs, MCP, and protocols · Coding and developer tools

Wisdom-Driven Knowledge Augmented Generation at Scale

Chin Keong Lam

Reasoning and models · Other / unclassified · RAG, context, and search

Writing Principles for Task-Tuned Prompt Engineering

Karina Nguyen

Reasoning and models · Evals · RAG, context, and search

WTF do people use Open Models for??

Eugene Cheah

Architecture · Reasoning and models · Coding and developer tools

WTF Is the Context Layer? The Missing Infrastructure for Production Agents

Prukalpa Sankar

Safety and governance · Agent engineering · Leadership

You Can't Prompt the Room: The Last Skill AI Won't Replace

Balázs Horváth

Agent engineering · Developer workflows and testing · Coding and developer tools

You Didn't Ship a Bug. You Just Wrote It for a Human.

Ravi Madabhushi

Safety and governance · APIs, MCP, and protocols · Agent engineering

You Might Not Need 50 Diffusion Steps

Ziv Ilan

Data and model adaptation · Infrastructure and deployment · Architecture

Your agent architecture has a half-life of 6 months

Dan Farrelly

Architecture · Infrastructure and deployment · Safety and governance

Your Agent Didn’t Fail. Your Harness Did.

Vinoth Govindarajan

Agent engineering · Other / unclassified · Developer workflows and testing

Your Agent Evolved. Your Evals Didn't.

Ameya Bhatawdekar

Evals · Architecture · RAG, context, and search

Your Agent Failed in Prod. Good Luck Reproducing It.

Tisha Chawla · Susheem Koul

Other / unclassified · Coding and developer tools · Observability and reliability

Your Agent Is an Infinite Canvas

Rachel Lee Nabors (RL Nabors)

APIs, MCP, and protocols · Agent engineering

Your agent is blindfolded

Johan Lajili

APIs, MCP, and protocols · Agent engineering · Coding and developer tools

Your Agent Is Wasting Tokens and You Don't Know It

[REDACTED:username]

RAG, context, and search · Observability and reliability · Reasoning and models

Your Agent's Biggest Lie: "I Searched the Web"

Rafael Levi

APIs, MCP, and protocols · Safety and governance · RAG, context, and search

Your Agents Need a Save Button

Hamza Tahir

Reasoning and models · Agent engineering · Evals

Your AI Agent Isn't an Engineer: The Art of Thoughtful Anthropomorphism

Rizel Scarlett

Leadership · APIs, MCP, and protocols · Enterprise

Your AI Product Will Fail Unless You Can Explain It

Veronica Hylak

Enterprise · Observability and reliability · Agent engineering

Your Attention Is the Bottleneck, Not Your Agents — Zack Proser, WorkOS

Zack Proser

Speech and audio · APIs, MCP, and protocols · Agent engineering

Your coding agent doesn't always follow your rules

Talha Sheikh

Coding and developer tools · Agent engineering · Evals

Your Coding Agent Just Got Cloned And Your Brain Isn't Ready

Rustin Banks

Developer workflows and testing · Coding and developer tools · Safety and governance

Your Coding Agent Should Do AI System Engineering

Ben Burtenshaw

Evals · Coding and developer tools · RAG, context, and search

Your Evals Are Meaningless (And Here’s How to Fix Them)

Mohak Sharma

Evals · Safety and governance

Your Finance Agent's Bottleneck Is You

Ramana Siddanth Emani

Finance · APIs, MCP, and protocols · Coding and developer tools

Your Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards

Dan Bjornn

Agent engineering · Architecture · Leadership

Your Insecure MCP Server Won't Survive Production — Tun Shwe, Lenses

Tun Shwe · Jeremy Frenay

Safety and governance · RAG, context, and search · Evals

Your LLM Deception Monitor Is Broken. The Fix Is in the Training Data - Sachin Kumar, LexisNexis

Sachin Kumar

Other / unclassified · Observability and reliability · Architecture

Your LLM Ran Out of Knowledge — Now What?

Other / unclassified · Evals · Reasoning and models

Your LLM Stack Is a 2008 Database With Better Marketing

Lovina Dmello

APIs, MCP, and protocols · Leadership · Safety and governance

Your MCP Server is Bad and You Should Feel Bad

Jeremiah Lowin

APIs, MCP, and protocols · RAG, context, and search

Your Moat Is Your Data Model

Mike Phipps

RAG, context, and search · Safety and governance · Leadership

Your Personal Open-Source Humanoid Robot for $8,999 — Jingxiang "JX" Mo, K-Scale Labs

Jingxiang "JX" Mo

Robotics and world models

Your realtime AI is ngmi — Sean DuBois (OpenAI), Kwindla Hultman Kramer (Daily)

Sean DuBois · Kwindla Hultman Kramer · Yaxin

Speech and audio · APIs, MCP, and protocols · Architecture